Intel and Heidelberg University Announced a New Collaboration to bring Radeon GPU Support to AI
Intel and the Heidelberg University (URZ) have announced a new Academic Center of Excellence to support and conduct research on the oneAPI platform. The collaboration followed Intel’s announcement of the oneAPI specification reaching 1.0 status.
In Intel’s journey, the milestone of 1.0 is significant as it enables collaborators to focus on adapting hardware to a standard, fixed implementation, worrying about the specification itself shifting rapidly beneath their feet.
URZ’s announcement begins by reiterating the raison d’etre of oneAPI itself, “URZ will focus its research and programming efforts on a fundamental high-performance computing (HPC) challenge where modern computers utilize different types of hardware for different calculations. Accelerators, including graphics processing units (GPUs) and field-programmable gate arrays (FPGAs), are used in combination with general compute processors (CPUs).”
“Using different types of hardware makes computers very powerful and provides versatility for a wide range of situations and workloads. Hardware heterogeneity, however, complicates software development for these computers, especially when specialized components from a variety of vendors are used in tandem.”
The reason for this complication is the requirement of separate programming models for many accelerated computing architectures. Therefore, software developers need to learn and use a different language for each processing unit.
Based on Khronos Groups’ SYCL standard for heterogeneous programming in C++, the oneAPI platform overcomes these challenges with its single, unified open development model for performance and productivity.
Professor Vincent Heuveline, CIO of Heidelberg University and URZ Managing Director says “For a scientific computing center to have access to this level of expertise and work together on an open standard with partners from around the globe, is a wonderful prospect.”
The university will help Intel fulfill it’s oneAPI being an effectively vendor-neutral and cross-hardware-platform effort. With this, they will also break the near-monopoly of Nvidia in the GPU accelerated ML ecosystem. Breaking its monopoly will benefit Intel’s own new and rising Xe Graphics platform.